Upload BioGPTForICD10Classification

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,149 @@
+{
+  "architectures": [
+    "BioGPTForICD10Classification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "code_to_idx": {
+    "D62": 0,
+    "D649": 1,
+    "D696": 2,
+    "E039": 3,
+    "E1122": 4,
+    "E119": 5,
+    "E669": 6,
+    "E785": 7,
+    "E871": 8,
+    "E872": 9,
+    "F17210": 10,
+    "F329": 11,
+    "F419": 12,
+    "G4700": 13,
+    "G4733": 14,
+    "G8929": 15,
+    "I10": 16,
+    "I110": 17,
+    "I129": 18,
+    "I130": 19,
+    "I2510": 20,
+    "I252": 21,
+    "I480": 22,
+    "I4891": 23,
+    "I5032": 24,
+    "J189": 25,
+    "J449": 26,
+    "J45909": 27,
+    "J9601": 28,
+    "K219": 29,
+    "K5900": 30,
+    "M109": 31,
+    "N179": 32,
+    "N183": 33,
+    "N189": 34,
+    "N390": 35,
+    "N400": 36,
+    "Y92230": 37,
+    "Y92239": 38,
+    "Y929": 39,
+    "Z23": 40,
+    "Z66": 41,
+    "Z7901": 42,
+    "Z7902": 43,
+    "Z794": 44,
+    "Z86718": 45,
+    "Z8673": 46,
+    "Z87891": 47,
+    "Z951": 48,
+    "Z955": 49
+  },
+  "dropout_rate": 0.2,
+  "enable_enhanced_attention": true,
+  "enable_enhanced_classifier": true,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "icd_codes": [
+    "D62",
+    "D649",
+    "D696",
+    "E039",
+    "E1122",
+    "E119",
+    "E669",
+    "E785",
+    "E871",
+    "E872",
+    "F17210",
+    "F329",
+    "F419",
+    "G4700",
+    "G4733",
+    "G8929",
+    "I10",
+    "I110",
+    "I129",
+    "I130",
+    "I2510",
+    "I252",
+    "I480",
+    "I4891",
+    "I5032",
+    "J189",
+    "J449",
+    "J45909",
+    "J9601",
+    "K219",
+    "K5900",
+    "M109",
+    "N179",
+    "N183",
+    "N189",
+    "N390",
+    "N400",
+    "Y92230",
+    "Y92239",
+    "Y929",
+    "Z23",
+    "Z66",
+    "Z7901",
+    "Z7902",
+    "Z794",
+    "Z86718",
+    "Z8673",
+    "Z87891",
+    "Z951",
+    "Z955"
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "learnable_icd_embeddings": true,
+  "max_position_embeddings": 1024,
+  "model_type": "biogpt-icd10",
+  "num_attention_heads": 16,
+  "num_attention_layers": 16,
+  "num_hidden_layers": 24,
+  "num_icd_codes": 50,
+  "performance_metrics": {
+    "aggregation_method": "mean",
+    "f1_macro": 0.6921683889110797,
+    "f1_micro": 0.7425923267783542,
+    "hamming_loss": 0.06360780339498354,
+    "precision_macro": 0.6175372765898886,
+    "precision_micro": 0.6570744275501688,
+    "recall_macro": 0.7921473231592516,
+    "recall_micro": 0.8537010843941537,
+    "subset_accuracy": 0.09880922219407144
+  },
+  "prediction_threshold": 0.25,
+  "scale_embedding": true,
+  "torch_dtype": "float32",
+  "training_details": {
+    "epoch": 31,
+    "timestamp": "2025-06-09T10:51:55.593755"
+  },
+  "transformers_version": "4.52.4",
+  "use_attention_pooling": true,
+  "use_cache": true,
+  "use_hierarchical_attention": true,
+  "vocab_size": 42384
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55cd7400f789555ebf3f4aca4330339ee0eeab1c2fe608eba2082fa7aed04589
+size 1700541064